Amazon cover image
Image from Amazon.com

Reinforcement learning : an introduction / Richard S. Sutton and Andrew G. Barto.

By: Contributor(s): Series: Adaptive computation and machine learningCambridge, Mass. : MIT Press, 1998Description: xviii, 322 pages : illustrations ; 24 cmContent type:
  • text
Media type:
  • unmediated
Carrier type:
  • volume
ISBN:
  • 0262193981
  • 9780262193986
Subject(s): LOC classification:
  • Q325.6 .S88 1998
Contents:
Contents -- Series Foreword -- Preface -- I. The Problem -- 1. Introduction -- 2. Evaluative Feedback -- 3. The Reinforcement Learning Problem -- II. Elementary Solution Methods -- 4. Dynamic Programming -- 5. Monte Carlo Methods -- 6. Temporal-Difference Learning -- III. A Unified View -- 7. Eligibility Traces -- 8. Generalization and Function Approximation -- 9. Planning and Learning -- 10. Dimensions of Reinforcement Learning -- 11. Case Studies -- References -- Summary of Notation -- Index.
Review: "In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability."--Jacket.
Holdings
Item type Current library Call number Copy number Status Date due Barcode Item holds
BOOK BOOK NCAR Library Mesa Lab Q325.6 .S88 1998 1 Available 50583020006866
Total holds: 0

Includes bibliographical references (pages 291-312) and index.

Contents -- Series Foreword -- Preface -- I. The Problem -- 1. Introduction -- 2. Evaluative Feedback -- 3. The Reinforcement Learning Problem -- II. Elementary Solution Methods -- 4. Dynamic Programming -- 5. Monte Carlo Methods -- 6. Temporal-Difference Learning -- III. A Unified View -- 7. Eligibility Traces -- 8. Generalization and Function Approximation -- 9. Planning and Learning -- 10. Dimensions of Reinforcement Learning -- 11. Case Studies -- References -- Summary of Notation -- Index.

"In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability."--Jacket.

Questions? Email library@ucar.edu.

Not finding what you are looking for? InterLibrary Loan.